May 25, 2026

Introducing Speech Engine

ElevenLabs Speech Engine adds real-time voice to your own chat agent or LLM. ElevenLabs handles speech-to-text, turn-taking, text-to-speech and browser playback while your server owns the agent logic and streams response text over a Speech Engine WebSocket. Use it when you want voice on a custom runtime rather than a fully hosted ElevenAgents configuration.

ElevenAgents

• Text behavior overrides: Added text_behavior_overrides, a per-ConversationInitiationSource map of BehaviorOverride objects with optional verbosity, output_format and interaction_budget fields for channel-specific agent behavior.
• Integration sources: Added Intercom, Telegram and Freshdesk.
• OTLP conversation traces: Get conversation details now accepts an optional format query parameter. Set format=otlp_traces to return OTLP-compatible trace data alongside the standard conversation payload.
• ASR keyword overrides: Added ASRConversationalConfigOverride and ASRConversationalConfigOverrideConfig schemas with optional keywords arrays, wired into conversation config client override models.
• Webhook auth metadata: Webhook tool configuration schemas now expose optional auth_resolved_params (string array) documenting URL placeholders resolved from the auth connection.

Music

• Generation mode: Added MusicGenerationMode (track, loop, ambience) and an optional generation_mode field on music prompt request bodies.
• Video to music model: Video to music (POST /v1/music/video-to-music) now accepts optional model_id (string, default music_v1).

ElevenCreative Studio

• Conversion credits: Chapter and voice conversion statistics response models now include optional credits_needed_to_convert (integer) indicating credits required before conversion.

Workspaces

• Resource types: Added studio_projects to WorkspaceResourceType.

SDK Releases

Python SDK

• v2.50.0 - Regenerated the SDK for the May 25, 2026 API schema.
• v2.49.1 - Updated Speech Engine API calls to return the full response object.
• v2.49.0 - Regenerated the SDK for the May 18–25, 2026 API schema, including ElevenAgents text behavior overrides, music generation_mode, and workspace studio_projects.

JavaScript SDK

• v2.50.0 - Added missing Music API methods and tests, and regenerated the SDK for the May 25, 2026 API schema.
• v2.49.1 - Updated Speech Engine API calls to return the full response object.
• v2.49.0 - Regenerated the SDK for the May 18–25, 2026 API schema, including ElevenAgents text behavior overrides, music generation_mode, and workspace studio_projects.

Packages

• @elevenlabs/client@1.8.1 - Fixed iOS Safari dropping the first agent message on WebSocket voice sessions by unlocking an AudioContext on the first user gesture and priming the playback graph after the audio worklet loads.
• @elevenlabs/convai-widget-core@0.12.8 and @elevenlabs/convai-widget-embed@0.12.8 - Style emotion and audio tags in voice transcripts when strip_audio_tags is off, and treat null top-level terms_html or terms_text as a kill switch for the terms and conditions modal.
• @elevenlabs/convai-widget-core@0.12.7 and @elevenlabs/convai-widget-embed@0.12.7 - Updated widget dependencies to @elevenlabs/client@1.8.1.

API